ml4gw.augmentations

This module contains transformations that may be useful for augmenting timeseries data during training

Classes

SignalInverter([prob])	Takes a tensor of timeseries of arbitrary dimension and randomly inverts i.e. \(h(t) \rightarrow -h(t)\) each timeseries with probability prob.
SignalReverser([prob])	Takes a tensor of timeseries of arbitrary dimension and randomly reverses i.e., \(h(t) \rightarrow h(-t)\).

class ml4gw.augmentations.SignalInverter(prob=0.5)

Bases: Module

Takes a tensor of timeseries of arbitrary dimension and randomly inverts i.e. \(h(t) \rightarrow -h(t)\) each timeseries with probability prob.

Parameters:

prob (float) -- Probability that a timeseries is inverted

forward(X)

Return type:

Float[Tensor, '*batch time']

Parameters:

X (Float[Tensor, '*batch time'])

class ml4gw.augmentations.SignalReverser(prob=0.5)

Bases: Module

Takes a tensor of timeseries of arbitrary dimension and randomly reverses i.e., \(h(t) \rightarrow h(-t)\). each timeseries with probability prob.

Parameters:

prob (float) -- Probability that a kernel is reversed

forward(X)

Return type:

Float[Tensor, '*batch time']

Parameters:

X (Float[Tensor, '*batch time'])